t5-base-zh-en
This model is a fine-tuned version of google-t5/t5-base on the covost2 dataset. It achieves the following results on the evaluation set:
- Loss: 3.6910
- Bleu: 0.1216
- Gen Len: 18.3285
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 1e-05
- train_batch_size: 8
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 2
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
|---|---|---|---|---|---|
| 3.7264 | 1.3407 | 1000 | 3.6910 | 0.1216 | 18.3285 |
Framework versions
- Transformers 4.51.2
- Pytorch 2.6.0+cu124
- Datasets 3.1.0
- Tokenizers 0.21.1